On Open-Universe Causal Reasoning

Abstract

We extend two kinds of causal models, structural equation models and simulation models, to infinite variable spaces. This enables a semantics for conditionals founded on a calculus of intervention, and axiomatization of causal reasoning for rich, expressive generative models -- including those in which a causal representation exists only implicitly -- in an open-universe setting. Further, we show that under suitable restrictions the two kinds of models are equivalent, perhaps surprisingly as their axiomatizations differ substantially in the general case. We give a series of complete axiomatizations in which the open-universe nature of the setting is seen to be essential.

UAI 2019

References in corpus (8)

• Learning the Structure of Dynamic Probabilistic Networks
• Church: a language for generative models
• Learning in Implicit Generative Models
• Deep Probabilistic Programming
• Nonparametric Bayesian Logic
• Group invariance principles for causal generative models
• Towards common-sense reasoning via conditional simulation: legacies of Turing in Artificial Intelligence
• Probabilistic Reasoning across the Causal Hierarchy

Cited by in corpus (1)

• Probabilistic Reasoning across the Causal Hierarchy